spree-multi-store
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and model specifications from the official Spree Commerce website to ensure accuracy during implementation. Evidence: Fetching documentation from spreecommerce.org for the multi-store model, marketplace model, and multi-tenant isolation.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to retrieve and process external documentation, creating an ingestion surface that could be exploited if those sources were compromised.
- Ingestion points: Retrieval of documentation from spreecommerce.org via WebFetch as instructed in SKILL.md.
- Boundary markers: The skill does not provide specific instructions or delimiters to isolate or ignore potential instructions embedded within the fetched documentation.
- Capability inventory: The agent is granted access to tools including Bash, Write, Edit, Read, Grep, Glob, WebSearch, and WebFetch.
- Sanitization: No mechanisms for validating or filtering the content of the external documentation are defined in the instructions.
Audit Metadata